© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2842
    Prev
    Next
    INDEX
    Explanations

    important disclaimers please read

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects expressions of gratitude or appreciative “thank you”–style praise in user comments.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     👇
    0.45
     suited
    0.44
    대로
    0.44
     `${
    0.43
     siehe
    0.43
     insgesamt
    0.42
     সেখানেই
    0.42
     आइए
    0.42
    अर
    0.41
     interpreted
    0.41
    POSITIVE LOGITS
    Ⲃ
    0.57
    ᓕ
    0.53
    ㄜ
    0.50
    iché
    0.48
    ereco
    0.48
    permut
    0.47
    rear
    0.45
    Ͻ
    0.45
    ദ
    0.44
    璐
    0.44
    Activations Density 0.122%

    No Known Activations